© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5644
    Prev
    Next
    INDEX
    Explanations

    tiny, refined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ра
    1.33
    т
    1.14
     bas
    1.09
    ை
    0.99
     بلوچستان
    0.99
    జేపీ
    0.99
    প্রিম
    0.97
     опро
    0.97
    북
    0.95
     त्रिभु
    0.95
    POSITIVE LOGITS
    }$:
    1.07
    izi
    1.05
     رولی
    1.00
    べる
    0.99
    ⚙
    0.99
    ONIUM
    0.98
     المنتج
    0.97
     Viper
    0.97
     girth
    0.96
     रझा
    0.95
    Activations Density 0.000%

    No Known Activations